Multi-Agent Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
138Avg Episode Reward
7
Feb 26, 2026
135.3Cumulative Reward
7
Feb 26, 2026
136.9Cumulative Reward
7
Feb 26, 2026
131.4Avg Episode Reward
7
Feb 26, 2026
134.9Avg Episode Reward
7
Feb 26, 2026
133.6Avg Episode Reward
7
Feb 26, 2026
134.7Cumulative Reward
7
Feb 26, 2026
94Win Rate
7
Feb 27, 2026
100Win Rate
7
Feb 27, 2026
9.802Normalized Mean Performance
7
Feb 26, 2026
19.71Test Win Rate
7
Feb 26, 2026
86.7Success Rate
6
Jul 7, 2026
31.9AUC
6
Jul 7, 2026
56.4AUC
6
Jul 7, 2026
60.9AUC
6
Jul 7, 2026
0.302AUC
6
Jul 7, 2026
0.808AUC
6
Jul 7, 2026
36.6AUC
6
Jul 7, 2026
0.157AUC
6
Jul 7, 2026
49.8AUC
6
Jul 7, 2026
55.4AUC
6
Jul 7, 2026
89Win Rate
6
Jun 24, 2026
69Win Rate
6
Jun 24, 2026
80Final Win Rate
6
Jun 24, 2026
72Win Rate
6
Jun 24, 2026